]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/liveleak.py
debian/changelog: Start new release.
[youtubedl] / youtube_dl / extractor / liveleak.py
1 from __future__ import unicode_literals
2
3 import json
4 import re
5
6 from .common import InfoExtractor
7 from ..utils import int_or_none
8
9
10 class LiveLeakIE(InfoExtractor):
11 _VALID_URL = r'^(?:http://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
12 _TESTS = [{
13 'url': 'http://www.liveleak.com/view?i=757_1364311680',
14 'md5': '0813c2430bea7a46bf13acf3406992f4',
15 'info_dict': {
16 'id': '757_1364311680',
17 'ext': 'mp4',
18 'description': 'extremely bad day for this guy..!',
19 'uploader': 'ljfriel2',
20 'title': 'Most unlucky car accident'
21 }
22 },
23 {
24 'url': 'http://www.liveleak.com/view?i=f93_1390833151',
25 'md5': 'd3f1367d14cc3c15bf24fbfbe04b9abf',
26 'info_dict': {
27 'id': 'f93_1390833151',
28 'ext': 'mp4',
29 'description': 'German Television Channel NDR does an exclusive interview with Edward Snowden.\r\nUploaded on LiveLeak cause German Television thinks the rest of the world isn\'t intereseted in Edward Snowden.',
30 'uploader': 'ARD_Stinkt',
31 'title': 'German Television does first Edward Snowden Interview (ENGLISH)',
32 }
33 },
34 {
35 'url': 'http://www.liveleak.com/view?i=4f7_1392687779',
36 'md5': '42c6d97d54f1db107958760788c5f48f',
37 'info_dict': {
38 'id': '4f7_1392687779',
39 'ext': 'mp4',
40 'description': "The guy with the cigarette seems amazingly nonchalant about the whole thing... I really hope my friends' reactions would be a bit stronger.\r\n\r\nAction-go to 0:55.",
41 'uploader': 'CapObveus',
42 'title': 'Man is Fatally Struck by Reckless Car While Packing up a Moving Truck',
43 'age_limit': 18,
44 }
45 }]
46
47 def _real_extract(self, url):
48 mobj = re.match(self._VALID_URL, url)
49 video_id = mobj.group('video_id')
50 webpage = self._download_webpage(url, video_id)
51
52 video_title = self._og_search_title(webpage).replace('LiveLeak.com -', '').strip()
53 video_description = self._og_search_description(webpage)
54 video_uploader = self._html_search_regex(
55 r'By:.*?(\w+)</a>', webpage, 'uploader', fatal=False)
56 age_limit = int_or_none(self._search_regex(
57 r'you confirm that you are ([0-9]+) years and over.',
58 webpage, 'age limit', default=None))
59
60 sources_raw = self._search_regex(
61 r'(?s)sources:\s*(\[.*?\]),', webpage, 'video URLs', default=None)
62 if sources_raw is None:
63 alt_source = self._search_regex(
64 r'(file: ".*?"),', webpage, 'video URL', default=None)
65 if alt_source:
66 sources_raw = '[{ %s}]' % alt_source
67 else:
68 # Maybe an embed?
69 embed_url = self._search_regex(
70 r'<iframe[^>]+src="(http://www.prochan.com/embed\?[^"]+)"',
71 webpage, 'embed URL')
72 return {
73 '_type': 'url_transparent',
74 'url': embed_url,
75 'id': video_id,
76 'title': video_title,
77 'description': video_description,
78 'uploader': video_uploader,
79 'age_limit': age_limit,
80 }
81
82 sources_json = re.sub(r'\s([a-z]+):\s', r'"\1": ', sources_raw)
83 sources = json.loads(sources_json)
84
85 formats = [{
86 'format_note': s.get('label'),
87 'url': s['file'],
88 } for s in sources]
89 self._sort_formats(formats)
90
91 return {
92 'id': video_id,
93 'title': video_title,
94 'description': video_description,
95 'uploader': video_uploader,
96 'formats': formats,
97 'age_limit': age_limit,
98 }